Automatic Speech Recognition
PEFT
Safetensors
English
whisper
lora
disfluent-speech
stuttering
accessibility
speech-disorders
verbatim-transcription
Eval Results (legacy)
Instructions to use nazarkozak/whisper-small-disfluent-verbatim-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nazarkozak/whisper-small-disfluent-verbatim-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("openai/whisper-small") model = PeftModel.from_pretrained(base_model, "nazarkozak/whisper-small-disfluent-verbatim-lora") - Notebooks
- Google Colab
- Kaggle
Upload preprocessor_config.json
Browse files- preprocessor_config.json +14 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"return_attention_mask": false,
|
| 13 |
+
"sampling_rate": 16000
|
| 14 |
+
}
|